hypothesis
active
hypothesis:during-pretraining-the-model-learns-distinct-harm-categories-and-during-finetuning-wires-them-into-general-harmful-request-features

During pretraining the model learns distinct harm categories and during finetuning wires them into general harmful-request features.

Suggested by dictionaries trained on pretraining data having few refusal features.

Source paper

extracted_from
On the Biology of a Large Language Model
Authors

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.